Open-Source Acceleration

QuantLib and ORE, 6 to 100x faster

Models the community has validated, at the speed of a proprietary library. AAD for every calculation. No vendor licence.

Schedule Call See Solution

Open models, production speed

A bank's choice has been an internal library it has to maintain or a vendor library it is locked into. QuantLib and ORE with AADC are the third option: models many people have read and tested, at production speed, with no vendor in the middle.

Common Frustrations

Sound familiar? These open-source challenges slow teams down

QuantLib/ORE too slow for production workloads?
Need AAD but can't implement it manually for all models?
Vendor licensing fees eating your budget?
Want community validation without performance trade-offs?
Greeks taking too long to compute?
Need proven models for regulatory compliance?
Calibration or Monte Carlo runs too slow for daily use?
Limited multithreading in standard builds?

The AADC Solution

AADC on QuantLib or ORE gives you the open models at proprietary speed, with AAD, multithreading and vectorisation included. Orders of magnitude over the standard build, on code a regulator can read.

150x Faster QuantLib/ORE
Production-grade performance from community code
Automatic AAD for All Models
Complete Greeks without manual implementation
Real-Time Greeks
Sub-second sensitivities for live trading
Zero Vendor Fees
Eliminate licensing costs entirely

Perfect For:

Organisations wanting to retire expensive vendor solutionsTeams seeking rapid deployment using proven algorithmsFirms needing regulatory compliance with accepted modelsAnyone valuing community validation and peer reviewTeams with QuantLib/ORE expertise looking for performance

Key Benefits

6-100x Faster

QuantLib/ORE at production speed

Automatic AAD

Greeks for all models, no manual work

No Licensing Fees

Eliminate vendor cost burden

Community Validated

Proven, peer-reviewed models

Proven Results

Client-Results

Tier-2 European Bank Achieves 15-20x Faster Risk with 70% Less Code

A Tier-2 European bank fixed the performance of its front-office risk infrastructure with MatLogica AADC. They achieved 15-20x speedups compared to manual adjoint differentiation, reduced overnight batch from 8+ hours to 2 hours, and eliminated 70% of their modelling codebase while unlocking new revenue streams.

  • ›15-20x faster risk vs manual adjoints
  • ›Overnight batch: 8+ hours to 2 hours
  • ›70% codebase reduction
  • ›50% grid cost savings
Read Full Case Study

SIMM Benchmark Results

Open-source ISDA-SIMM project accelerated with AADC

AADC vs GPU: 47× Faster SIMM with Exact Gradients

AADC C++ computes ISDA SIMM sensitivities at 34,000 evaluations/sec on CPU, 47× faster than GPU pathwise differentiation on NVIDIA H100. GPU brute-force fails to converge at scale due to noisy finite-difference gradients.

  • 34,000 SIMM evaluations/sec with AADC C++ on CPU
  • 47× faster than GPU Pathwise on NVIDIA H100
  • GPU brute-force fails to converge at 500+ trades
View Benchmark

SIMM Optimisation: 33K Evals/sec, 25× Faster than GPU

AADC C++ computes SIMM trade allocation gradients at 33,580 evals/sec, 25× faster than GPU. Optimises a 50K trade portfolio in 19 ms with 1-2 iterations to converge.

  • 33,580 evaluations/second with AADC C++
  • 25× faster than GPU implementations
  • 19 ms to optimise 50K trade portfolio
View Benchmark

Legacy Optimisation

AADC goes into the analytics you already have, with few code changes. The years of business logic in the code stay; the run time drops 6 to 100x and the Greeks come with it.

Learn More

Greenfield Development

Use AADC to develop C++/Python models faster, without optimisation concerns. Get production-grade performance and automatic AAD from day one. Focus on models, not infrastructure.

Learn More

Cloud Cost Optimisation

A workload that runs 6 to 1000x faster needs a fraction of the instances for a fraction of the time: 50 to 99% off the bill. Only compiled kernels go to the cloud; the source stays home.

Learn More

Ready to Accelerate Your Open-Source Stack?

See AADC accelerating QuantLib and ORE in action.

Schedule Technical Call

Frequently Asked Questions

How much faster is ORE with AADC?
We've demonstrated 245x acceleration of ORE (Open Source Risk Engine) with AADC. Specific speedups depend on your workload, but 6-150x improvements are typical across QuantLib and ORE calculations.
Do I need to modify QuantLib source code?
No, AADC works through type replacement at compile time. Your QuantLib code remains unchanged. You simply build with AADC-enabled types instead of standard double types.
Can this really replace our vendor solution?
Many organisations use AADC + QuantLib/ORE as a direct vendor replacement. You get community-validated models with production-grade performance. The key difference is full ownership and control of your analytics stack.
How does AADC compare to manual AAD implementation?
Manual AAD implementation for QuantLib typically takes months to years and requires deep expertise. AADC provides automatic AAD for all models immediately, with better performance and no maintenance burden.